Radar / Ideas / ProofGate: a merge queue that proves…

ProofGate: a merge queue that proves agent-written code safe before it ships

daily ideaambitiousJEV confidence 0.45JEV monetization 0.552026-11-11
OutcomeA merge queue that never ships a bad agent PR

The problem

Agent-written code is flooding pull requests, and the AI reviewers teams already pay for can only pattern-match: they catch style issues and likely bugs, but cannot prove a security property. A Meta engineer's viral post about shipping code nobody understands drew thousands of comments from engineers in the same spot, and one documented case had an AI-generated password-hashing function with a salt flaw that only surfaced in an audit months later.

The idea

A GitHub App merge queue. A cheap decision model triages every agent PR and routes only the security-critical diffs — crypto, auth, payments, data handling — to a formal-verification agent that generates proofs for those paths, in the style of the system that verified Signal's crypto code. Everything else gets risk-aware auto-approval. A PR merges only when its risky paths carry proofs or a human signs off, and every proof is attached to the merge as an artifact.

Why now

Three capabilities landed within days of each other: AlphaProof Code showed agents formally verifying Signal's real cryptographic code in four weeks (10 November); decision models like Strands Decider answer in tens of milliseconds, making per-PR triage nearly free; and LiveReview proved teams want risk-aware auto-approval instead of reviewing everything by hand.

What it combines

AlphaProof Code's formal verification of real code plus Strands Decider's near-free routing decisions plus LiveReview's risk-aware auto-approval. Verification without triage is too slow and expensive to run on every PR; triage without verification is just smarter linting; auto-approval without either is a gamble. Together they make a queue that is both fast and provably safe on the paths that matter.

MVP

Weekend MVP: a GitHub Action that runs on PRs touching a configurable list of sensitive paths, calls a decision model to classify the diff, and for crypto/auth files runs a small proof check on one function, posting the result as a check. Skip: the full queue, auto-merge, and multi-repo proofs.

How it makes money

Budget owner: the VP Engineering or Head of AppSec, out of the budget already paying for code review and static analysis. Pricing anchor: CodeRabbit Advanced at $72 per developer per month (coderabbit.ai/pricing) — ProofGate prices at or above that tier because it replaces both the review seat and part of the SAST spend. Willingness-to-pay evidence: teams already pay $24-72 per developer per month for AI review that only pattern-matches, and the viral Hacker News thread on shipping code nobody understands shows engineers actively demanding a real answer to this exact problem.

The moat

The proof corpus is a per-repo data advantage: every verified path becomes a reusable proof artifact, so the queue gets faster and cheaper on each repo the longer it runs — a new entrant starts at zero proofs. GitHub's own review tooling is velocity-oriented and would have to rebuild around proof generation and take on liability for 'verified' claims; pattern-matching incumbents cannot bolt formal verification onto a suggester in one quarter.

Distribution

GitHub App sold to engineering-platform and AppSec teams; the wedge is security teams at companies running AI-coding mandates, where the volume of agent PRs has already outrun human review. B2B, per-developer seats like the review tools it replaces.

Why it wins

CodeRabbit, Greptile and Qodo pattern-match and suggest fixes; ProofGate proves. The deliverable is not a comment thread but a mathematical guarantee on the security-critical paths, attached to the merge as an artifact a security team can audit.

Risks

Formal verification is slow and can fail on real-world code with side effects, so proof coverage may stay narrow. The MVP de-risks it by scoping to one function class and measuring the proof success rate before promising queue-wide coverage.

Build it with

Repo to start from

proofgate: a GitHub Action and merge queue that routes security-critical agent PRs to formal verification and auto-approves the rest.

Evidence

Get the week's best AI launches, plus 3 ideas worth building

One email every Saturday. Ranked by traction, not hype. Free.